From 0764db9b49c932b89ee4d9e3236dff4bb07b4a66 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 11 Feb 2022 16:32:32 -0800 Subject: mm: memcg: synchronize objcg lists with a dedicated spinlock Alexander reported a circular lock dependency revealed by the mmap1 ltp test: LOCKDEP_CIRCULAR (suite: ltp, case: mtest06 (mmap1)) WARNING: possible circular locking dependency detected 5.17.0-20220113.rc0.git0.f2211f194038.300.fc35.s390x+debug #1 Not tainted ------------------------------------------------------ mmap1/202299 is trying to acquire lock: 00000001892c0188 (css_set_lock){..-.}-{2:2}, at: obj_cgroup_release+0x4a/0xe0 but task is already holding lock: 00000000ca3b3818 (&sighand->siglock){-.-.}-{2:2}, at: force_sig_info_to_task+0x38/0x180 which lock already depends on the new lock. the existing dependency chain (in reverse order) is: -> #1 (&sighand->siglock){-.-.}-{2:2}: __lock_acquire+0x604/0xbd8 lock_acquire.part.0+0xe2/0x238 lock_acquire+0xb0/0x200 _raw_spin_lock_irqsave+0x6a/0xd8 __lock_task_sighand+0x90/0x190 cgroup_freeze_task+0x2e/0x90 cgroup_migrate_execute+0x11c/0x608 cgroup_update_dfl_csses+0x246/0x270 cgroup_subtree_control_write+0x238/0x518 kernfs_fop_write_iter+0x13e/0x1e0 new_sync_write+0x100/0x190 vfs_write+0x22c/0x2d8 ksys_write+0x6c/0xf8 __do_syscall+0x1da/0x208 system_call+0x82/0xb0 -> #0 (css_set_lock){..-.}-{2:2}: check_prev_add+0xe0/0xed8 validate_chain+0x736/0xb20 __lock_acquire+0x604/0xbd8 lock_acquire.part.0+0xe2/0x238 lock_acquire+0xb0/0x200 _raw_spin_lock_irqsave+0x6a/0xd8 obj_cgroup_release+0x4a/0xe0 percpu_ref_put_many.constprop.0+0x150/0x168 drain_obj_stock+0x94/0xe8 refill_obj_stock+0x94/0x278 obj_cgroup_charge+0x164/0x1d8 kmem_cache_alloc+0xac/0x528 __sigqueue_alloc+0x150/0x308 __send_signal+0x260/0x550 send_signal+0x7e/0x348 force_sig_info_to_task+0x104/0x180 force_sig_fault+0x48/0x58 __do_pgm_check+0x120/0x1f0 pgm_check_handler+0x11e/0x180 other info that might help us debug this: Possible unsafe locking scenario: CPU0 CPU1 ---- ---- lock(&sighand->siglock); lock(css_set_lock); lock(&sighand->siglock); lock(css_set_lock); *** DEADLOCK *** 2 locks held by mmap1/202299: #0: 00000000ca3b3818 (&sighand->siglock){-.-.}-{2:2}, at: force_sig_info_to_task+0x38/0x180 #1: 00000001892ad560 (rcu_read_lock){....}-{1:2}, at: percpu_ref_put_many.constprop.0+0x0/0x168 stack backtrace: CPU: 15 PID: 202299 Comm: mmap1 Not tainted 5.17.0-20220113.rc0.git0.f2211f194038.300.fc35.s390x+debug #1 Hardware name: IBM 3906 M04 704 (LPAR) Call Trace: dump_stack_lvl+0x76/0x98 check_noncircular+0x136/0x158 check_prev_add+0xe0/0xed8 validate_chain+0x736/0xb20 __lock_acquire+0x604/0xbd8 lock_acquire.part.0+0xe2/0x238 lock_acquire+0xb0/0x200 _raw_spin_lock_irqsave+0x6a/0xd8 obj_cgroup_release+0x4a/0xe0 percpu_ref_put_many.constprop.0+0x150/0x168 drain_obj_stock+0x94/0xe8 refill_obj_stock+0x94/0x278 obj_cgroup_charge+0x164/0x1d8 kmem_cache_alloc+0xac/0x528 __sigqueue_alloc+0x150/0x308 __send_signal+0x260/0x550 send_signal+0x7e/0x348 force_sig_info_to_task+0x104/0x180 force_sig_fault+0x48/0x58 __do_pgm_check+0x120/0x1f0 pgm_check_handler+0x11e/0x180 INFO: lockdep is turned off. In this example a slab allocation from __send_signal() caused a refilling and draining of a percpu objcg stock, resulted in a releasing of another non-related objcg. Objcg release path requires taking the css_set_lock, which is used to synchronize objcg lists. This can create a circular dependency with the sighandler lock, which is taken with the locked css_set_lock by the freezer code (to freeze a task). In general it seems that using css_set_lock to synchronize objcg lists makes any slab allocations and deallocation with the locked css_set_lock and any intervened locks risky. To fix the problem and make the code more robust let's stop using css_set_lock to synchronize objcg lists and use a new dedicated spinlock instead. Link: https://lkml.kernel.org/r/Yfm1IHmoGdyUR81T@carbon.dhcp.thefacebook.com Fixes: bf4f059954dc ("mm: memcg/slab: obj_cgroup API") Signed-off-by: Roman Gushchin Reported-by: Alexander Egorenkov Tested-by: Alexander Egorenkov Reviewed-by: Waiman Long Acked-by: Tejun Heo Reviewed-by: Shakeel Butt Reviewed-by: Jeremy Linton Tested-by: Jeremy Linton Cc: Johannes Weiner Cc: Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) (limited to 'include/linux/memcontrol.h') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index b72d75141e12..0abbd685703b 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -219,7 +219,7 @@ struct obj_cgroup { struct mem_cgroup *memcg; atomic_t nr_charged_bytes; union { - struct list_head list; + struct list_head list; /* protected by objcg_lock */ struct rcu_head rcu; }; }; @@ -315,7 +315,8 @@ struct mem_cgroup { #ifdef CONFIG_MEMCG_KMEM int kmemcg_id; struct obj_cgroup __rcu *objcg; - struct list_head objcg_list; /* list of inherited objcgs */ + /* list of inherited objcgs, protected by objcg_lock */ + struct list_head objcg_list; #endif MEMCG_PADDING(_pad2_); -- cgit v1.2.3 From a8c49af3be5f0b4e105ef678bcf14ef102c270be Mon Sep 17 00:00:00 2001 From: Yosry Ahmed Date: Tue, 22 Mar 2022 14:40:10 -0700 Subject: memcg: add per-memcg total kernel memory stat Currently memcg stats show several types of kernel memory: kernel stack, page tables, sock, vmalloc, and slab. However, there are other allocations with __GFP_ACCOUNT (or supersets such as GFP_KERNEL_ACCOUNT) that are not accounted in any of those stats, a few examples are: - various kvm allocations (e.g. allocated pages to create vcpus) - io_uring - tmp_page in pipes during pipe_write() - bpf ringbuffers - unix sockets Keeping track of the total kernel memory is essential for the ease of migration from cgroup v1 to v2 as there are large discrepancies between v1's kmem.usage_in_bytes and the sum of the available kernel memory stats in v2. Adding separate memcg stats for all __GFP_ACCOUNT kernel allocations is an impractical maintenance burden as there a lot of those all over the kernel code, with more use cases likely to show up in the future. Therefore, add a "kernel" memcg stat that is analogous to kmem page counter, with added benefits such as using rstat infrastructure which aggregates stats more efficiently. Additionally, this provides a lighter alternative in case the legacy kmem is deprecated in the future [yosryahmed@google.com: v2] Link: https://lkml.kernel.org/r/20220203193856.972500-1-yosryahmed@google.com Link: https://lkml.kernel.org/r/20220201200823.3283171-1-yosryahmed@google.com Signed-off-by: Yosry Ahmed Acked-by: Shakeel Butt Acked-by: Johannes Weiner Cc: Michal Hocko Cc: Muchun Song Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/admin-guide/cgroup-v2.rst | 5 +++++ include/linux/memcontrol.h | 1 + mm/memcontrol.c | 27 +++++++++++++++++++++------ 3 files changed, 27 insertions(+), 6 deletions(-) (limited to 'include/linux/memcontrol.h') diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst index 5aa368d165da..69d7a6983f78 100644 --- a/Documentation/admin-guide/cgroup-v2.rst +++ b/Documentation/admin-guide/cgroup-v2.rst @@ -1301,6 +1301,11 @@ PAGE_SIZE multiple when read back. Amount of memory used to cache filesystem data, including tmpfs and shared memory. + kernel (npn) + Amount of total kernel memory, including + (kernel_stack, pagetables, percpu, vmalloc, slab) in + addition to other kernel memory use cases. + kernel_stack Amount of memory allocated to kernel stacks. diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 0abbd685703b..8612d7dd0859 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -34,6 +34,7 @@ enum memcg_stat_item { MEMCG_SOCK, MEMCG_PERCPU_B, MEMCG_VMALLOC, + MEMCG_KMEM, MEMCG_NR_STAT, }; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 209e66893da6..e64a276837b0 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1371,6 +1371,7 @@ struct memory_stat { static const struct memory_stat memory_stats[] = { { "anon", NR_ANON_MAPPED }, { "file", NR_FILE_PAGES }, + { "kernel", MEMCG_KMEM }, { "kernel_stack", NR_KERNEL_STACK_KB }, { "pagetables", NR_PAGETABLE }, { "percpu", MEMCG_PERCPU_B }, @@ -2114,6 +2115,7 @@ static DEFINE_MUTEX(percpu_charge_mutex); static void drain_obj_stock(struct obj_stock *stock); static bool obj_stock_flush_required(struct memcg_stock_pcp *stock, struct mem_cgroup *root_memcg); +static void memcg_account_kmem(struct mem_cgroup *memcg, int nr_pages); #else static inline void drain_obj_stock(struct obj_stock *stock) @@ -2124,6 +2126,9 @@ static bool obj_stock_flush_required(struct memcg_stock_pcp *stock, { return false; } +static void memcg_account_kmem(struct mem_cgroup *memcg, int nr_pages) +{ +} #endif /** @@ -2979,6 +2984,18 @@ static void memcg_free_cache_id(int id) ida_simple_remove(&memcg_cache_ida, id); } +static void memcg_account_kmem(struct mem_cgroup *memcg, int nr_pages) +{ + mod_memcg_state(memcg, MEMCG_KMEM, nr_pages); + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) { + if (nr_pages > 0) + page_counter_charge(&memcg->kmem, nr_pages); + else + page_counter_uncharge(&memcg->kmem, -nr_pages); + } +} + + /* * obj_cgroup_uncharge_pages: uncharge a number of kernel pages from a objcg * @objcg: object cgroup to uncharge @@ -2991,8 +3008,7 @@ static void obj_cgroup_uncharge_pages(struct obj_cgroup *objcg, memcg = get_mem_cgroup_from_objcg(objcg); - if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) - page_counter_uncharge(&memcg->kmem, nr_pages); + memcg_account_kmem(memcg, -nr_pages); refill_stock(memcg, nr_pages); css_put(&memcg->css); @@ -3018,8 +3034,7 @@ static int obj_cgroup_charge_pages(struct obj_cgroup *objcg, gfp_t gfp, if (ret) goto out; - if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) - page_counter_charge(&memcg->kmem, nr_pages); + memcg_account_kmem(memcg, nr_pages); out: css_put(&memcg->css); @@ -6801,8 +6816,8 @@ static void uncharge_batch(const struct uncharge_gather *ug) page_counter_uncharge(&ug->memcg->memory, ug->nr_memory); if (do_memsw_account()) page_counter_uncharge(&ug->memcg->memsw, ug->nr_memory); - if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && ug->nr_kmem) - page_counter_uncharge(&ug->memcg->kmem, ug->nr_kmem); + if (ug->nr_kmem) + memcg_account_kmem(ug->memcg, -ug->nr_kmem); memcg_oom_recover(ug->memcg); } -- cgit v1.2.3 From 486bc7060cb510fa60cb85a013d5ed51ce0fe456 Mon Sep 17 00:00:00 2001 From: Wei Yang Date: Tue, 22 Mar 2022 14:40:16 -0700 Subject: mm/memcg: retrieve parent memcg from css.parent The parent we get from page_counter is correct, while this is two different hierarchy. Let's retrieve the parent memcg from css.parent just like parent_cs(), blkcg_parent(), etc. Link: https://lkml.kernel.org/r/20220201004643.8391-2-richard.weiyang@gmail.com Signed-off-by: Wei Yang Reviewed-by: Muchun Song Acked-by: Michal Hocko Reviewed-by: Roman Gushchin Reviewed-by: Shakeel Butt Cc: Roman Gushchin Cc: Johannes Weiner Cc: Vladimir Davydov Cc: Yang Shi Cc: Suren Baghdasaryan Cc: Vlastimil Babka Cc: Mike Rapoport Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include/linux/memcontrol.h') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 8612d7dd0859..ef4b445392a9 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -842,9 +842,7 @@ static inline struct mem_cgroup *lruvec_memcg(struct lruvec *lruvec) */ static inline struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) { - if (!memcg->memory.parent) - return NULL; - return mem_cgroup_from_counter(memcg->memory.parent, memory); + return mem_cgroup_from_css(memcg->css.parent); } static inline bool mem_cgroup_is_descendant(struct mem_cgroup *memcg, -- cgit v1.2.3 From 88f2ef73fd66491a2f9a82373d22ca6540f23c62 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Tue, 22 Mar 2022 14:40:56 -0700 Subject: mm: introduce kmem_cache_alloc_lru We currently allocate scope for every memcg to be able to tracked on every superblock instantiated in the system, regardless of whether that superblock is even accessible to that memcg. These huge memcg counts come from container hosts where memcgs are confined to just a small subset of the total number of superblocks that instantiated at any given point in time. For these systems with huge container counts, list_lru does not need the capability of tracking every memcg on every superblock. What it comes down to is that adding the memcg to the list_lru at the first insert. So introduce kmem_cache_alloc_lru to allocate objects and its list_lru. In the later patch, we will convert all inode and dentry allocation from kmem_cache_alloc to kmem_cache_alloc_lru. Link: https://lkml.kernel.org/r/20220228122126.37293-3-songmuchun@bytedance.com Signed-off-by: Muchun Song Cc: Alex Shi Cc: Anna Schumaker Cc: Chao Yu Cc: Dave Chinner Cc: Fam Zheng Cc: Jaegeuk Kim Cc: Johannes Weiner Cc: Kari Argillander Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Qi Zheng Cc: Roman Gushchin Cc: Shakeel Butt Cc: Theodore Ts'o Cc: Trond Myklebust Cc: Vladimir Davydov Cc: Vlastimil Babka Cc: Wei Yang Cc: Xiongchun Duan Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/list_lru.h | 4 ++ include/linux/memcontrol.h | 14 ++++++ include/linux/slab.h | 3 ++ mm/list_lru.c | 104 +++++++++++++++++++++++++++++++++++++++++---- mm/memcontrol.c | 14 ------ mm/slab.c | 39 +++++++++++------ mm/slab.h | 25 +++++++++-- mm/slob.c | 6 +++ mm/slub.c | 42 ++++++++++++------ 9 files changed, 198 insertions(+), 53 deletions(-) (limited to 'include/linux/memcontrol.h') diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index 729a27b6ff53..ab912c49334f 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -56,6 +56,8 @@ struct list_lru { struct list_head list; int shrinker_id; bool memcg_aware; + /* protects ->mlrus->mlru[i] */ + spinlock_t lock; /* for cgroup aware lrus points to per cgroup lists, otherwise NULL */ struct list_lru_memcg __rcu *mlrus; #endif @@ -72,6 +74,8 @@ int __list_lru_init(struct list_lru *lru, bool memcg_aware, #define list_lru_init_memcg(lru, shrinker) \ __list_lru_init((lru), true, NULL, shrinker) +int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru, + gfp_t gfp); int memcg_update_all_list_lrus(int num_memcgs); void memcg_drain_all_list_lrus(int src_idx, struct mem_cgroup *dst_memcg); diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index ef4b445392a9..b636732f0c14 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -524,6 +524,20 @@ static inline struct mem_cgroup *page_memcg_check(struct page *page) return (struct mem_cgroup *)(memcg_data & ~MEMCG_DATA_FLAGS_MASK); } +static inline struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg) +{ + struct mem_cgroup *memcg; + + rcu_read_lock(); +retry: + memcg = obj_cgroup_memcg(objcg); + if (unlikely(!css_tryget(&memcg->css))) + goto retry; + rcu_read_unlock(); + + return memcg; +} + #ifdef CONFIG_MEMCG_KMEM /* * folio_memcg_kmem - Check if the folio has the memcg_kmem flag set. diff --git a/include/linux/slab.h b/include/linux/slab.h index 5b6193fd8bd9..e6addaf91afd 100644 --- a/include/linux/slab.h +++ b/include/linux/slab.h @@ -135,6 +135,7 @@ #include +struct list_lru; struct mem_cgroup; /* * struct kmem_cache related prototypes @@ -416,6 +417,8 @@ static __always_inline unsigned int __kmalloc_index(size_t size, void *__kmalloc(size_t size, gfp_t flags) __assume_kmalloc_alignment __alloc_size(1); void *kmem_cache_alloc(struct kmem_cache *s, gfp_t flags) __assume_slab_alignment __malloc; +void *kmem_cache_alloc_lru(struct kmem_cache *s, struct list_lru *lru, + gfp_t gfpflags) __assume_slab_alignment __malloc; void kmem_cache_free(struct kmem_cache *s, void *objp); /* diff --git a/mm/list_lru.c b/mm/list_lru.c index 7d1356241aa8..bffa80527723 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -13,6 +13,7 @@ #include #include #include "slab.h" +#include "internal.h" #ifdef CONFIG_MEMCG_KMEM static LIST_HEAD(memcg_list_lrus); @@ -338,22 +339,30 @@ static void memcg_destroy_list_lru_range(struct list_lru_memcg *mlrus, kfree(mlrus->mlru[i]); } +static struct list_lru_per_memcg *memcg_init_list_lru_one(gfp_t gfp) +{ + int nid; + struct list_lru_per_memcg *mlru; + + mlru = kmalloc(struct_size(mlru, node, nr_node_ids), gfp); + if (!mlru) + return NULL; + + for_each_node(nid) + init_one_lru(&mlru->node[nid]); + + return mlru; +} + static int memcg_init_list_lru_range(struct list_lru_memcg *mlrus, int begin, int end) { int i; for (i = begin; i < end; i++) { - int nid; - struct list_lru_per_memcg *mlru; - - mlru = kmalloc(struct_size(mlru, node, nr_node_ids), GFP_KERNEL); - if (!mlru) + mlrus->mlru[i] = memcg_init_list_lru_one(GFP_KERNEL); + if (!mlrus->mlru[i]) goto fail; - - for_each_node(nid) - init_one_lru(&mlru->node[nid]); - mlrus->mlru[i] = mlru; } return 0; fail: @@ -370,6 +379,8 @@ static int memcg_init_list_lru(struct list_lru *lru, bool memcg_aware) if (!memcg_aware) return 0; + spin_lock_init(&lru->lock); + mlrus = kvmalloc(struct_size(mlrus, mlru, size), GFP_KERNEL); if (!mlrus) return -ENOMEM; @@ -416,8 +427,11 @@ static int memcg_update_list_lru(struct list_lru *lru, int old_size, int new_siz return -ENOMEM; } + spin_lock_irq(&lru->lock); memcpy(&new->mlru, &old->mlru, flex_array_size(new, mlru, old_size)); rcu_assign_pointer(lru->mlrus, new); + spin_unlock_irq(&lru->lock); + kvfree_rcu(old, rcu); return 0; } @@ -502,6 +516,78 @@ void memcg_drain_all_list_lrus(int src_idx, struct mem_cgroup *dst_memcg) memcg_drain_list_lru(lru, src_idx, dst_memcg); mutex_unlock(&list_lrus_mutex); } + +static bool memcg_list_lru_allocated(struct mem_cgroup *memcg, + struct list_lru *lru) +{ + bool allocated; + int idx; + + idx = memcg->kmemcg_id; + if (unlikely(idx < 0)) + return true; + + rcu_read_lock(); + allocated = !!rcu_dereference(lru->mlrus)->mlru[idx]; + rcu_read_unlock(); + + return allocated; +} + +int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru, + gfp_t gfp) +{ + int i; + unsigned long flags; + struct list_lru_memcg *mlrus; + struct list_lru_memcg_table { + struct list_lru_per_memcg *mlru; + struct mem_cgroup *memcg; + } *table; + + if (!list_lru_memcg_aware(lru) || memcg_list_lru_allocated(memcg, lru)) + return 0; + + gfp &= GFP_RECLAIM_MASK; + table = kmalloc_array(memcg->css.cgroup->level, sizeof(*table), gfp); + if (!table) + return -ENOMEM; + + /* + * Because the list_lru can be reparented to the parent cgroup's + * list_lru, we should make sure that this cgroup and all its + * ancestors have allocated list_lru_per_memcg. + */ + for (i = 0; memcg; memcg = parent_mem_cgroup(memcg), i++) { + if (memcg_list_lru_allocated(memcg, lru)) + break; + + table[i].memcg = memcg; + table[i].mlru = memcg_init_list_lru_one(gfp); + if (!table[i].mlru) { + while (i--) + kfree(table[i].mlru); + kfree(table); + return -ENOMEM; + } + } + + spin_lock_irqsave(&lru->lock, flags); + mlrus = rcu_dereference_protected(lru->mlrus, true); + while (i--) { + int index = table[i].memcg->kmemcg_id; + + if (mlrus->mlru[index]) + kfree(table[i].mlru); + else + mlrus->mlru[index] = table[i].mlru; + } + spin_unlock_irqrestore(&lru->lock, flags); + + kfree(table); + + return 0; +} #else static int memcg_init_list_lru(struct list_lru *lru, bool memcg_aware) { diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 85a259515e91..52835528eb2a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2805,20 +2805,6 @@ static void commit_charge(struct folio *folio, struct mem_cgroup *memcg) folio->memcg_data = (unsigned long)memcg; } -static struct mem_cgroup *get_mem_cgroup_from_objcg(struct obj_cgroup *objcg) -{ - struct mem_cgroup *memcg; - - rcu_read_lock(); -retry: - memcg = obj_cgroup_memcg(objcg); - if (unlikely(!css_tryget(&memcg->css))) - goto retry; - rcu_read_unlock(); - - return memcg; -} - #ifdef CONFIG_MEMCG_KMEM /* * The allocated objcg pointers array is not accounted directly. diff --git a/mm/slab.c b/mm/slab.c index ddf5737c63d9..d9dec7a8fd79 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -3211,7 +3211,7 @@ slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid, size_t orig_ bool init = false; flags &= gfp_allowed_mask; - cachep = slab_pre_alloc_hook(cachep, &objcg, 1, flags); + cachep = slab_pre_alloc_hook(cachep, NULL, &objcg, 1, flags); if (unlikely(!cachep)) return NULL; @@ -3287,7 +3287,8 @@ __do_cache_alloc(struct kmem_cache *cachep, gfp_t flags) #endif /* CONFIG_NUMA */ static __always_inline void * -slab_alloc(struct kmem_cache *cachep, gfp_t flags, size_t orig_size, unsigned long caller) +slab_alloc(struct kmem_cache *cachep, struct list_lru *lru, gfp_t flags, + size_t orig_size, unsigned long caller) { unsigned long save_flags; void *objp; @@ -3295,7 +3296,7 @@ slab_alloc(struct kmem_cache *cachep, gfp_t flags, size_t orig_size, unsigned lo bool init = false; flags &= gfp_allowed_mask; - cachep = slab_pre_alloc_hook(cachep, &objcg, 1, flags); + cachep = slab_pre_alloc_hook(cachep, lru, &objcg, 1, flags); if (unlikely(!cachep)) return NULL; @@ -3484,6 +3485,18 @@ void ___cache_free(struct kmem_cache *cachep, void *objp, __free_one(ac, objp); } +static __always_inline +void *__kmem_cache_alloc_lru(struct kmem_cache *cachep, struct list_lru *lru, + gfp_t flags) +{ + void *ret = slab_alloc(cachep, lru, flags, cachep->object_size, _RET_IP_); + + trace_kmem_cache_alloc(_RET_IP_, ret, + cachep->object_size, cachep->size, flags); + + return ret; +} + /** * kmem_cache_alloc - Allocate an object * @cachep: The cache to allocate from. @@ -3496,15 +3509,17 @@ void ___cache_free(struct kmem_cache *cachep, void *objp, */ void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags) { - void *ret = slab_alloc(cachep, flags, cachep->object_size, _RET_IP_); - - trace_kmem_cache_alloc(_RET_IP_, ret, - cachep->object_size, cachep->size, flags); - - return ret; + return __kmem_cache_alloc_lru(cachep, NULL, flags); } EXPORT_SYMBOL(kmem_cache_alloc); +void *kmem_cache_alloc_lru(struct kmem_cache *cachep, struct list_lru *lru, + gfp_t flags) +{ + return __kmem_cache_alloc_lru(cachep, lru, flags); +} +EXPORT_SYMBOL(kmem_cache_alloc_lru); + static __always_inline void cache_alloc_debugcheck_after_bulk(struct kmem_cache *s, gfp_t flags, size_t size, void **p, unsigned long caller) @@ -3521,7 +3536,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, size_t i; struct obj_cgroup *objcg = NULL; - s = slab_pre_alloc_hook(s, &objcg, size, flags); + s = slab_pre_alloc_hook(s, NULL, &objcg, size, flags); if (!s) return 0; @@ -3562,7 +3577,7 @@ kmem_cache_alloc_trace(struct kmem_cache *cachep, gfp_t flags, size_t size) { void *ret; - ret = slab_alloc(cachep, flags, size, _RET_IP_); + ret = slab_alloc(cachep, NULL, flags, size, _RET_IP_); ret = kasan_kmalloc(cachep, ret, size, flags); trace_kmalloc(_RET_IP_, ret, @@ -3689,7 +3704,7 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags, cachep = kmalloc_slab(size, flags); if (unlikely(ZERO_OR_NULL_PTR(cachep))) return cachep; - ret = slab_alloc(cachep, flags, size, caller); + ret = slab_alloc(cachep, NULL, flags, size, caller); ret = kasan_kmalloc(cachep, ret, size, flags); trace_kmalloc(caller, ret, diff --git a/mm/slab.h b/mm/slab.h index c7f2abc2b154..fd7ae2024897 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -231,6 +231,7 @@ struct kmem_cache { #include #include #include +#include /* * State of the slab allocator. @@ -472,6 +473,7 @@ static inline size_t obj_full_size(struct kmem_cache *s) * Returns false if the allocation should fail. */ static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s, + struct list_lru *lru, struct obj_cgroup **objcgp, size_t objects, gfp_t flags) { @@ -487,13 +489,26 @@ static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s, if (!objcg) return true; - if (obj_cgroup_charge(objcg, flags, objects * obj_full_size(s))) { - obj_cgroup_put(objcg); - return false; + if (lru) { + int ret; + struct mem_cgroup *memcg; + + memcg = get_mem_cgroup_from_objcg(objcg); + ret = memcg_list_lru_alloc(memcg, lru, flags); + css_put(&memcg->css); + + if (ret) + goto out; } + if (obj_cgroup_charge(objcg, flags, objects * obj_full_size(s))) + goto out; + *objcgp = objcg; return true; +out: + obj_cgroup_put(objcg); + return false; } static inline void memcg_slab_post_alloc_hook(struct kmem_cache *s, @@ -598,6 +613,7 @@ static inline void memcg_free_slab_cgroups(struct slab *slab) } static inline bool memcg_slab_pre_alloc_hook(struct kmem_cache *s, + struct list_lru *lru, struct obj_cgroup **objcgp, size_t objects, gfp_t flags) { @@ -697,6 +713,7 @@ static inline size_t slab_ksize(const struct kmem_cache *s) } static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s, + struct list_lru *lru, struct obj_cgroup **objcgp, size_t size, gfp_t flags) { @@ -707,7 +724,7 @@ static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s, if (should_failslab(s, flags)) return NULL; - if (!memcg_slab_pre_alloc_hook(s, objcgp, size, flags)) + if (!memcg_slab_pre_alloc_hook(s, lru, objcgp, size, flags)) return NULL; return s; diff --git a/mm/slob.c b/mm/slob.c index 60c5842215f1..8a8795520361 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -635,6 +635,12 @@ void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags) } EXPORT_SYMBOL(kmem_cache_alloc); + +void *kmem_cache_alloc_lru(struct kmem_cache *cachep, struct list_lru *lru, gfp_t flags) +{ + return slob_alloc_node(cachep, flags, NUMA_NO_NODE); +} +EXPORT_SYMBOL(kmem_cache_alloc_lru); #ifdef CONFIG_NUMA void *__kmalloc_node(size_t size, gfp_t gfp, int node) { diff --git a/mm/slub.c b/mm/slub.c index 261474092e43..07cdd999c3fe 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -3131,7 +3131,7 @@ static __always_inline void maybe_wipe_obj_freeptr(struct kmem_cache *s, * * Otherwise we can simply pick the next object from the lockless free list. */ -static __always_inline void *slab_alloc_node(struct kmem_cache *s, +static __always_inline void *slab_alloc_node(struct kmem_cache *s, struct list_lru *lru, gfp_t gfpflags, int node, unsigned long addr, size_t orig_size) { void *object; @@ -3141,7 +3141,7 @@ static __always_inline void *slab_alloc_node(struct kmem_cache *s, struct obj_cgroup *objcg = NULL; bool init = false; - s = slab_pre_alloc_hook(s, &objcg, 1, gfpflags); + s = slab_pre_alloc_hook(s, lru, &objcg, 1, gfpflags); if (!s) return NULL; @@ -3232,27 +3232,41 @@ out: return object; } -static __always_inline void *slab_alloc(struct kmem_cache *s, +static __always_inline void *slab_alloc(struct kmem_cache *s, struct list_lru *lru, gfp_t gfpflags, unsigned long addr, size_t orig_size) { - return slab_alloc_node(s, gfpflags, NUMA_NO_NODE, addr, orig_size); + return slab_alloc_node(s, lru, gfpflags, NUMA_NO_NODE, addr, orig_size); } -void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags) +static __always_inline +void *__kmem_cache_alloc_lru(struct kmem_cache *s, struct list_lru *lru, + gfp_t gfpflags) { - void *ret = slab_alloc(s, gfpflags, _RET_IP_, s->object_size); + void *ret = slab_alloc(s, lru, gfpflags, _RET_IP_, s->object_size); trace_kmem_cache_alloc(_RET_IP_, ret, s->object_size, s->size, gfpflags); return ret; } + +void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags) +{ + return __kmem_cache_alloc_lru(s, NULL, gfpflags); +} EXPORT_SYMBOL(kmem_cache_alloc); +void *kmem_cache_alloc_lru(struct kmem_cache *s, struct list_lru *lru, + gfp_t gfpflags) +{ + return __kmem_cache_alloc_lru(s, lru, gfpflags); +} +EXPORT_SYMBOL(kmem_cache_alloc_lru); + #ifdef CONFIG_TRACING void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size) { - void *ret = slab_alloc(s, gfpflags, _RET_IP_, size); + void *ret = slab_alloc(s, NULL, gfpflags, _RET_IP_, size); trace_kmalloc(_RET_IP_, ret, size, s->size, gfpflags); ret = kasan_kmalloc(s, ret, size, gfpflags); return ret; @@ -3263,7 +3277,7 @@ EXPORT_SYMBOL(kmem_cache_alloc_trace); #ifdef CONFIG_NUMA void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node) { - void *ret = slab_alloc_node(s, gfpflags, node, _RET_IP_, s->object_size); + void *ret = slab_alloc_node(s, NULL, gfpflags, node, _RET_IP_, s->object_size); trace_kmem_cache_alloc_node(_RET_IP_, ret, s->object_size, s->size, gfpflags, node); @@ -3277,7 +3291,7 @@ void *kmem_cache_alloc_node_trace(struct kmem_cache *s, gfp_t gfpflags, int node, size_t size) { - void *ret = slab_alloc_node(s, gfpflags, node, _RET_IP_, size); + void *ret = slab_alloc_node(s, NULL, gfpflags, node, _RET_IP_, size); trace_kmalloc_node(_RET_IP_, ret, size, s->size, gfpflags, node); @@ -3667,7 +3681,7 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, struct obj_cgroup *objcg = NULL; /* memcg and kmem_cache debug support */ - s = slab_pre_alloc_hook(s, &objcg, size, flags); + s = slab_pre_alloc_hook(s, NULL, &objcg, size, flags); if (unlikely(!s)) return false; /* @@ -4417,7 +4431,7 @@ void *__kmalloc(size_t size, gfp_t flags) if (unlikely(ZERO_OR_NULL_PTR(s))) return s; - ret = slab_alloc(s, flags, _RET_IP_, size); + ret = slab_alloc(s, NULL, flags, _RET_IP_, size); trace_kmalloc(_RET_IP_, ret, size, s->size, flags); @@ -4465,7 +4479,7 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node) if (unlikely(ZERO_OR_NULL_PTR(s))) return s; - ret = slab_alloc_node(s, flags, node, _RET_IP_, size); + ret = slab_alloc_node(s, NULL, flags, node, _RET_IP_, size); trace_kmalloc_node(_RET_IP_, ret, size, s->size, flags, node); @@ -4923,7 +4937,7 @@ void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller) if (unlikely(ZERO_OR_NULL_PTR(s))) return s; - ret = slab_alloc(s, gfpflags, caller, size); + ret = slab_alloc(s, NULL, gfpflags, caller, size); /* Honor the call site pointer we received. */ trace_kmalloc(caller, ret, size, s->size, gfpflags); @@ -4954,7 +4968,7 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags, if (unlikely(ZERO_OR_NULL_PTR(s))) return s; - ret = slab_alloc_node(s, gfpflags, node, caller, size); + ret = slab_alloc_node(s, NULL, gfpflags, node, caller, size); /* Honor the call site pointer we received. */ trace_kmalloc_node(caller, ret, size, s->size, gfpflags, node); -- cgit v1.2.3 From bbca91cca9a902de2e9907370e9c1e0a3d1aab0f Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Tue, 22 Mar 2022 14:41:25 -0700 Subject: mm: list_lru: replace linear array with xarray If we run 10k containers in the system, the size of the list_lru_memcg->lrus can be ~96KB per list_lru. When we decrease the number containers, the size of the array will not be shrinked. It is not scalable. The xarray is a good choice for this case. We can save a lot of memory when there are tens of thousands continers in the system. If we use xarray, we also can remove the logic code of resizing array, which can simplify the code. [akpm@linux-foundation.org: remove unused local] Link: https://lkml.kernel.org/r/20220228122126.37293-13-songmuchun@bytedance.com Signed-off-by: Muchun Song Cc: Alex Shi Cc: Anna Schumaker Cc: Chao Yu Cc: Dave Chinner Cc: Fam Zheng Cc: Jaegeuk Kim Cc: Johannes Weiner Cc: Kari Argillander Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Qi Zheng Cc: Roman Gushchin Cc: Shakeel Butt Cc: Theodore Ts'o Cc: Trond Myklebust Cc: Vladimir Davydov Cc: Vlastimil Babka Cc: Wei Yang Cc: Xiongchun Duan Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/list_lru.h | 13 +-- include/linux/memcontrol.h | 23 ----- mm/list_lru.c | 203 +++++++++++++++------------------------------ mm/memcontrol.c | 77 ++--------------- 4 files changed, 73 insertions(+), 243 deletions(-) (limited to 'include/linux/memcontrol.h') diff --git a/include/linux/list_lru.h b/include/linux/list_lru.h index 4b00fd8cb373..572c263561ac 100644 --- a/include/linux/list_lru.h +++ b/include/linux/list_lru.h @@ -11,6 +11,7 @@ #include #include #include +#include struct mem_cgroup; @@ -37,12 +38,6 @@ struct list_lru_per_memcg { struct list_lru_one node[]; }; -struct list_lru_memcg { - struct rcu_head rcu; - /* array of per cgroup lists, indexed by memcg_cache_id */ - struct list_lru_per_memcg __rcu *mlru[]; -}; - struct list_lru_node { /* protects all lists on the node, including per cgroup */ spinlock_t lock; @@ -57,10 +52,7 @@ struct list_lru { struct list_head list; int shrinker_id; bool memcg_aware; - /* protects ->mlrus->mlru[i] */ - spinlock_t lock; - /* for cgroup aware lrus points to per cgroup lists, otherwise NULL */ - struct list_lru_memcg __rcu *mlrus; + struct xarray xa; #endif }; @@ -77,7 +69,6 @@ int __list_lru_init(struct list_lru *lru, bool memcg_aware, int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru, gfp_t gfp); -int memcg_update_all_list_lrus(int num_memcgs); void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *parent); /** diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index b636732f0c14..066b7a3b8a9e 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1685,18 +1685,6 @@ void obj_cgroup_uncharge(struct obj_cgroup *objcg, size_t size); extern struct static_key_false memcg_kmem_enabled_key; -extern int memcg_nr_cache_ids; -void memcg_get_cache_ids(void); -void memcg_put_cache_ids(void); - -/* - * Helper macro to loop through all memcg-specific caches. Callers must still - * check if the cache is valid (it is either valid or NULL). - * the slab_mutex must be held when looping through those caches - */ -#define for_each_memcg_cache_index(_idx) \ - for ((_idx) = 0; (_idx) < memcg_nr_cache_ids; (_idx)++) - static inline bool memcg_kmem_enabled(void) { return static_branch_likely(&memcg_kmem_enabled_key); @@ -1753,9 +1741,6 @@ static inline void __memcg_kmem_uncharge_page(struct page *page, int order) { } -#define for_each_memcg_cache_index(_idx) \ - for (; NULL; ) - static inline bool memcg_kmem_enabled(void) { return false; @@ -1766,14 +1751,6 @@ static inline int memcg_cache_id(struct mem_cgroup *memcg) return -1; } -static inline void memcg_get_cache_ids(void) -{ -} - -static inline void memcg_put_cache_ids(void) -{ -} - static inline struct mem_cgroup *mem_cgroup_from_obj(void *p) { return NULL; diff --git a/mm/list_lru.c b/mm/list_lru.c index 488dacd1f8ff..3fdae1688f82 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -52,21 +52,12 @@ static int lru_shrinker_id(struct list_lru *lru) static inline struct list_lru_one * list_lru_from_memcg_idx(struct list_lru *lru, int nid, int idx) { - struct list_lru_memcg *mlrus; - struct list_lru_node *nlru = &lru->node[nid]; - - /* - * Either lock or RCU protects the array of per cgroup lists - * from relocation (see memcg_update_list_lru). - */ - mlrus = rcu_dereference_check(lru->mlrus, lockdep_is_held(&nlru->lock)); - if (mlrus && idx >= 0) { - struct list_lru_per_memcg *mlru; + if (list_lru_memcg_aware(lru) && idx >= 0) { + struct list_lru_per_memcg *mlru = xa_load(&lru->xa, idx); - mlru = rcu_dereference_check(mlrus->mlru[idx], true); return mlru ? &mlru->node[nid] : NULL; } - return &nlru->lru; + return &lru->node[nid].lru; } static inline struct list_lru_one * @@ -77,7 +68,7 @@ list_lru_from_kmem(struct list_lru *lru, int nid, void *ptr, struct list_lru_one *l = &nlru->lru; struct mem_cgroup *memcg = NULL; - if (!lru->mlrus) + if (!list_lru_memcg_aware(lru)) goto out; memcg = mem_cgroup_from_obj(ptr); @@ -309,16 +300,20 @@ unsigned long list_lru_walk_node(struct list_lru *lru, int nid, unsigned long *nr_to_walk) { long isolated = 0; - int memcg_idx; isolated += list_lru_walk_one(lru, nid, NULL, isolate, cb_arg, nr_to_walk); + +#ifdef CONFIG_MEMCG_KMEM if (*nr_to_walk > 0 && list_lru_memcg_aware(lru)) { - for_each_memcg_cache_index(memcg_idx) { + struct list_lru_per_memcg *mlru; + unsigned long index; + + xa_for_each(&lru->xa, index, mlru) { struct list_lru_node *nlru = &lru->node[nid]; spin_lock(&nlru->lock); - isolated += __list_lru_walk_one(lru, nid, memcg_idx, + isolated += __list_lru_walk_one(lru, nid, index, isolate, cb_arg, nr_to_walk); spin_unlock(&nlru->lock); @@ -327,6 +322,8 @@ unsigned long list_lru_walk_node(struct list_lru *lru, int nid, break; } } +#endif + return isolated; } EXPORT_SYMBOL_GPL(list_lru_walk_node); @@ -338,15 +335,6 @@ static void init_one_lru(struct list_lru_one *l) } #ifdef CONFIG_MEMCG_KMEM -static void memcg_destroy_list_lru_range(struct list_lru_memcg *mlrus, - int begin, int end) -{ - int i; - - for (i = begin; i < end; i++) - kfree(mlrus->mlru[i]); -} - static struct list_lru_per_memcg *memcg_init_list_lru_one(gfp_t gfp) { int nid; @@ -364,14 +352,7 @@ static struct list_lru_per_memcg *memcg_init_list_lru_one(gfp_t gfp) static void memcg_list_lru_free(struct list_lru *lru, int src_idx) { - struct list_lru_memcg *mlrus; - struct list_lru_per_memcg *mlru; - - spin_lock_irq(&lru->lock); - mlrus = rcu_dereference_protected(lru->mlrus, true); - mlru = rcu_dereference_protected(mlrus->mlru[src_idx], true); - rcu_assign_pointer(mlrus->mlru[src_idx], NULL); - spin_unlock_irq(&lru->lock); + struct list_lru_per_memcg *mlru = xa_erase_irq(&lru->xa, src_idx); /* * The __list_lru_walk_one() can walk the list of this node. @@ -383,78 +364,27 @@ static void memcg_list_lru_free(struct list_lru *lru, int src_idx) kvfree_rcu(mlru, rcu); } -static int memcg_init_list_lru(struct list_lru *lru, bool memcg_aware) +static inline void memcg_init_list_lru(struct list_lru *lru, bool memcg_aware) { - struct list_lru_memcg *mlrus; - int size = memcg_nr_cache_ids; - + if (memcg_aware) + xa_init_flags(&lru->xa, XA_FLAGS_LOCK_IRQ); lru->memcg_aware = memcg_aware; - if (!memcg_aware) - return 0; - - spin_lock_init(&lru->lock); - - mlrus = kvzalloc(struct_size(mlrus, mlru, size), GFP_KERNEL); - if (!mlrus) - return -ENOMEM; - - RCU_INIT_POINTER(lru->mlrus, mlrus); - - return 0; } static void memcg_destroy_list_lru(struct list_lru *lru) { - struct list_lru_memcg *mlrus; + XA_STATE(xas, &lru->xa, 0); + struct list_lru_per_memcg *mlru; if (!list_lru_memcg_aware(lru)) return; - /* - * This is called when shrinker has already been unregistered, - * and nobody can use it. So, there is no need to use kvfree_rcu(). - */ - mlrus = rcu_dereference_protected(lru->mlrus, true); - memcg_destroy_list_lru_range(mlrus, 0, memcg_nr_cache_ids); - kvfree(mlrus); -} - -static int memcg_update_list_lru(struct list_lru *lru, int old_size, int new_size) -{ - struct list_lru_memcg *old, *new; - - BUG_ON(old_size > new_size); - - old = rcu_dereference_protected(lru->mlrus, - lockdep_is_held(&list_lrus_mutex)); - new = kvmalloc(struct_size(new, mlru, new_size), GFP_KERNEL); - if (!new) - return -ENOMEM; - - spin_lock_irq(&lru->lock); - memcpy(&new->mlru, &old->mlru, flex_array_size(new, mlru, old_size)); - memset(&new->mlru[old_size], 0, flex_array_size(new, mlru, new_size - old_size)); - rcu_assign_pointer(lru->mlrus, new); - spin_unlock_irq(&lru->lock); - - kvfree_rcu(old, rcu); - return 0; -} - -int memcg_update_all_list_lrus(int new_size) -{ - int ret = 0; - struct list_lru *lru; - int old_size = memcg_nr_cache_ids; - - mutex_lock(&list_lrus_mutex); - list_for_each_entry(lru, &memcg_list_lrus, list) { - ret = memcg_update_list_lru(lru, old_size, new_size); - if (ret) - break; + xas_lock_irq(&xas); + xas_for_each(&xas, mlru, ULONG_MAX) { + kfree(mlru); + xas_store(&xas, NULL); } - mutex_unlock(&list_lrus_mutex); - return ret; + xas_unlock_irq(&xas); } static void memcg_reparent_list_lru_node(struct list_lru *lru, int nid, @@ -521,7 +451,7 @@ void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *paren struct mem_cgroup *child; child = mem_cgroup_from_css(css); - child->kmemcg_id = parent->kmemcg_id; + WRITE_ONCE(child->kmemcg_id, parent->kmemcg_id); } rcu_read_unlock(); @@ -531,21 +461,12 @@ void memcg_reparent_list_lrus(struct mem_cgroup *memcg, struct mem_cgroup *paren mutex_unlock(&list_lrus_mutex); } -static bool memcg_list_lru_allocated(struct mem_cgroup *memcg, - struct list_lru *lru) +static inline bool memcg_list_lru_allocated(struct mem_cgroup *memcg, + struct list_lru *lru) { - bool allocated; - int idx; - - idx = memcg->kmemcg_id; - if (unlikely(idx < 0)) - return true; + int idx = memcg->kmemcg_id; - rcu_read_lock(); - allocated = !!rcu_access_pointer(rcu_dereference(lru->mlrus)->mlru[idx]); - rcu_read_unlock(); - - return allocated; + return idx < 0 || xa_load(&lru->xa, idx); } int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru, @@ -553,11 +474,11 @@ int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru, { int i; unsigned long flags; - struct list_lru_memcg *mlrus; struct list_lru_memcg_table { struct list_lru_per_memcg *mlru; struct mem_cgroup *memcg; } *table; + XA_STATE(xas, &lru->xa, 0); if (!list_lru_memcg_aware(lru) || memcg_list_lru_allocated(memcg, lru)) return 0; @@ -586,27 +507,48 @@ int memcg_list_lru_alloc(struct mem_cgroup *memcg, struct list_lru *lru, } } - spin_lock_irqsave(&lru->lock, flags); - mlrus = rcu_dereference_protected(lru->mlrus, true); + xas_lock_irqsave(&xas, flags); while (i--) { - int index = table[i].memcg->kmemcg_id; + int index = READ_ONCE(table[i].memcg->kmemcg_id); struct list_lru_per_memcg *mlru = table[i].mlru; - if (index < 0 || rcu_dereference_protected(mlrus->mlru[index], true)) + xas_set(&xas, index); +retry: + if (unlikely(index < 0 || xas_error(&xas) || xas_load(&xas))) { kfree(mlru); - else - rcu_assign_pointer(mlrus->mlru[index], mlru); + } else { + xas_store(&xas, mlru); + if (xas_error(&xas) == -ENOMEM) { + xas_unlock_irqrestore(&xas, flags); + if (xas_nomem(&xas, gfp)) + xas_set_err(&xas, 0); + xas_lock_irqsave(&xas, flags); + /* + * The xas lock has been released, this memcg + * can be reparented before us. So reload + * memcg id. More details see the comments + * in memcg_reparent_list_lrus(). + */ + index = READ_ONCE(table[i].memcg->kmemcg_id); + if (index < 0) + xas_set_err(&xas, 0); + else if (!xas_error(&xas) && index != xas.xa_index) + xas_set(&xas, index); + goto retry; + } + } } - spin_unlock_irqrestore(&lru->lock, flags); - + /* xas_nomem() is used to free memory instead of memory allocation. */ + if (xas.xa_alloc) + xas_nomem(&xas, gfp); + xas_unlock_irqrestore(&xas, flags); kfree(table); - return 0; + return xas_error(&xas); } #else -static int memcg_init_list_lru(struct list_lru *lru, bool memcg_aware) +static inline void memcg_init_list_lru(struct list_lru *lru, bool memcg_aware) { - return 0; } static void memcg_destroy_list_lru(struct list_lru *lru) @@ -618,7 +560,6 @@ int __list_lru_init(struct list_lru *lru, bool memcg_aware, struct lock_class_key *key, struct shrinker *shrinker) { int i; - int err = -ENOMEM; #ifdef CONFIG_MEMCG_KMEM if (shrinker) @@ -626,11 +567,10 @@ int __list_lru_init(struct list_lru *lru, bool memcg_aware, else lru->shrinker_id = -1; #endif - memcg_get_cache_ids(); lru->node = kcalloc(nr_node_ids, sizeof(*lru->node), GFP_KERNEL); if (!lru->node) - goto out; + return -ENOMEM; for_each_node(i) { spin_lock_init(&lru->node[i].lock); @@ -639,18 +579,10 @@ int __list_lru_init(struct list_lru *lru, bool memcg_aware, init_one_lru(&lru->node[i].lru); } - err = memcg_init_list_lru(lru, memcg_aware); - if (err) { - kfree(lru->node); - /* Do this so a list_lru_destroy() doesn't crash: */ - lru->node = NULL; - goto out; - } - + memcg_init_list_lru(lru, memcg_aware); list_lru_register(lru); -out: - memcg_put_cache_ids(); - return err; + + return 0; } EXPORT_SYMBOL_GPL(__list_lru_init); @@ -660,8 +592,6 @@ void list_lru_destroy(struct list_lru *lru) if (!lru->node) return; - memcg_get_cache_ids(); - list_lru_unregister(lru); memcg_destroy_list_lru(lru); @@ -671,6 +601,5 @@ void list_lru_destroy(struct list_lru *lru) #ifdef CONFIG_MEMCG_KMEM lru->shrinker_id = -1; #endif - memcg_put_cache_ids(); } EXPORT_SYMBOL_GPL(list_lru_destroy); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index c36b0a0dbc19..68eb62d10c48 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -351,42 +351,17 @@ static void memcg_reparent_objcgs(struct mem_cgroup *memcg, * This will be used as a shrinker list's index. * The main reason for not using cgroup id for this: * this works better in sparse environments, where we have a lot of memcgs, - * but only a few kmem-limited. Or also, if we have, for instance, 200 - * memcgs, and none but the 200th is kmem-limited, we'd have to have a - * 200 entry array for that. - * - * The current size of the caches array is stored in memcg_nr_cache_ids. It - * will double each time we have to increase it. + * but only a few kmem-limited. */ static DEFINE_IDA(memcg_cache_ida); -int memcg_nr_cache_ids; - -/* Protects memcg_nr_cache_ids */ -static DECLARE_RWSEM(memcg_cache_ids_sem); - -void memcg_get_cache_ids(void) -{ - down_read(&memcg_cache_ids_sem); -} - -void memcg_put_cache_ids(void) -{ - up_read(&memcg_cache_ids_sem); -} /* - * MIN_SIZE is different than 1, because we would like to avoid going through - * the alloc/free process all the time. In a small machine, 4 kmem-limited - * cgroups is a reasonable guess. In the future, it could be a parameter or - * tunable, but that is strictly not necessary. - * * MAX_SIZE should be as large as the number of cgrp_ids. Ideally, we could get * this constant directly from cgroup, but it is understandable that this is * better kept as an internal representation in cgroup.c. In any case, the * cgrp_id space is not getting any smaller, and we don't have to necessarily * increase ours as well if it increases. */ -#define MEMCG_CACHES_MIN_SIZE 4 #define MEMCG_CACHES_MAX_SIZE MEM_CGROUP_ID_MAX /* @@ -2944,49 +2919,6 @@ __always_inline struct obj_cgroup *get_obj_cgroup_from_current(void) return objcg; } -static int memcg_alloc_cache_id(void) -{ - int id, size; - int err; - - id = ida_simple_get(&memcg_cache_ida, - 0, MEMCG_CACHES_MAX_SIZE, GFP_KERNEL); - if (id < 0) - return id; - - if (id < memcg_nr_cache_ids) - return id; - - /* - * There's no space for the new id in memcg_caches arrays, - * so we have to grow them. - */ - down_write(&memcg_cache_ids_sem); - - size = 2 * (id + 1); - if (size < MEMCG_CACHES_MIN_SIZE) - size = MEMCG_CACHES_MIN_SIZE; - else if (size > MEMCG_CACHES_MAX_SIZE) - size = MEMCG_CACHES_MAX_SIZE; - - err = memcg_update_all_list_lrus(size); - if (!err) - memcg_nr_cache_ids = size; - - up_write(&memcg_cache_ids_sem); - - if (err) { - ida_simple_remove(&memcg_cache_ida, id); - return err; - } - return id; -} - -static void memcg_free_cache_id(int id) -{ - ida_simple_remove(&memcg_cache_ida, id); -} - static void memcg_account_kmem(struct mem_cgroup *memcg, int nr_pages) { mod_memcg_state(memcg, MEMCG_KMEM, nr_pages); @@ -3673,13 +3605,14 @@ static int memcg_online_kmem(struct mem_cgroup *memcg) if (unlikely(mem_cgroup_is_root(memcg))) return 0; - memcg_id = memcg_alloc_cache_id(); + memcg_id = ida_alloc_max(&memcg_cache_ida, MEMCG_CACHES_MAX_SIZE - 1, + GFP_KERNEL); if (memcg_id < 0) return memcg_id; objcg = obj_cgroup_alloc(); if (!objcg) { - memcg_free_cache_id(memcg_id); + ida_free(&memcg_cache_ida, memcg_id); return -ENOMEM; } objcg->memcg = memcg; @@ -3723,7 +3656,7 @@ static void memcg_offline_kmem(struct mem_cgroup *memcg) */ memcg_reparent_list_lrus(memcg, parent); - memcg_free_cache_id(kmemcg_id); + ida_free(&memcg_cache_ida, kmemcg_id); } #else static int memcg_online_kmem(struct mem_cgroup *memcg) -- cgit v1.2.3 From 7c52f65de40ff0e44f821559eb61931d368a4c48 Mon Sep 17 00:00:00 2001 From: Muchun Song Date: Tue, 22 Mar 2022 14:41:38 -0700 Subject: mm: memcontrol: rename memcg_cache_id to memcg_kmem_id The memcg_cache_id() introduced by commit 2633d7a02823 ("slab/slub: consider a memcg parameter in kmem_create_cache") is used to index in the kmem_cache->memcg_params->memcg_caches array. Since kmem_cache->memcg_params.memcg_caches has been removed by commit 9855609bde03 ("mm: memcg/slab: use a single set of kmem_caches for all accounted allocations"). So the name does not need to reflect cache related. Just rename it to memcg_kmem_id. And it can reflect kmem related. Link: https://lkml.kernel.org/r/20220228122126.37293-17-songmuchun@bytedance.com Signed-off-by: Muchun Song Cc: Alex Shi Cc: Anna Schumaker Cc: Chao Yu Cc: Dave Chinner Cc: Fam Zheng Cc: Jaegeuk Kim Cc: Johannes Weiner Cc: Kari Argillander Cc: Matthew Wilcox (Oracle) Cc: Michal Hocko Cc: Qi Zheng Cc: Roman Gushchin Cc: Shakeel Butt Cc: Theodore Ts'o Cc: Trond Myklebust Cc: Vladimir Davydov Cc: Vlastimil Babka Cc: Wei Yang Cc: Xiongchun Duan Cc: Yang Shi Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/memcontrol.h | 4 ++-- mm/list_lru.c | 8 ++++---- 2 files changed, 6 insertions(+), 6 deletions(-) (limited to 'include/linux/memcontrol.h') diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h index 066b7a3b8a9e..a68dce3873fc 100644 --- a/include/linux/memcontrol.h +++ b/include/linux/memcontrol.h @@ -1708,7 +1708,7 @@ static inline void memcg_kmem_uncharge_page(struct page *page, int order) * A helper for accessing memcg's kmem_id, used for getting * corresponding LRU lists. */ -static inline int memcg_cache_id(struct mem_cgroup *memcg) +static inline int memcg_kmem_id(struct mem_cgroup *memcg) { return memcg ? memcg->kmemcg_id : -1; } @@ -1746,7 +1746,7 @@ static inline bool memcg_kmem_enabled(void) return false; } -static inline int memcg_cache_id(struct mem_cgroup *memcg) +static inline int memcg_kmem_id(struct mem_cgroup *memcg) { return -1; } diff --git a/mm/list_lru.c b/mm/list_lru.c index 1e740febc96e..ba76428ceece 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -75,7 +75,7 @@ list_lru_from_kmem(struct list_lru *lru, int nid, void *ptr, if (!memcg) goto out; - l = list_lru_from_memcg_idx(lru, nid, memcg_cache_id(memcg)); + l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg)); out: if (memcg_ptr) *memcg_ptr = memcg; @@ -182,7 +182,7 @@ unsigned long list_lru_count_one(struct list_lru *lru, long count; rcu_read_lock(); - l = list_lru_from_memcg_idx(lru, nid, memcg_cache_id(memcg)); + l = list_lru_from_memcg_idx(lru, nid, memcg_kmem_id(memcg)); count = l ? READ_ONCE(l->nr_items) : 0; rcu_read_unlock(); @@ -273,7 +273,7 @@ list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg, unsigned long ret; spin_lock(&nlru->lock); - ret = __list_lru_walk_one(lru, nid, memcg_cache_id(memcg), isolate, + ret = __list_lru_walk_one(lru, nid, memcg_kmem_id(memcg), isolate, cb_arg, nr_to_walk); spin_unlock(&nlru->lock); return ret; @@ -289,7 +289,7 @@ list_lru_walk_one_irq(struct list_lru *lru, int nid, struct mem_cgroup *memcg, unsigned long ret; spin_lock_irq(&nlru->lock); - ret = __list_lru_walk_one(lru, nid, memcg_cache_id(memcg), isolate, + ret = __list_lru_walk_one(lru, nid, memcg_kmem_id(memcg), isolate, cb_arg, nr_to_walk); spin_unlock_irq(&nlru->lock); return ret; -- cgit v1.2.3